sh0ck0r/Snowpiercer-15B-v4-heretic

Full fine-tune vs SillyTilly/ServiceNow-AI-Apriel-Nemotron-15b-Thinker-Chatml. Fine-tune: 100% of the weights changed, across 50 of 50 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 41/101, MLP 150/150, Attention 200/200

2 derivatives checked